Beruflich Dokumente
Kultur Dokumente
06 ISSN2305-8269
International Journal of Engineering and Applied Sciences
© 2012 - 2014 EAAS & ARF. All rights reserved
www.eaas-journal.org
Lecturer, Emmanuel Alayande College of Education, PMB 1010, Oyo, Oyo State, Nigeria
E-mail: olanloyeo@yahoo.com
ABSTRACT
Most of the people especially in the Africa sub-region preferred using a 2-wheeled vehicle to a 4 –wheeled vehicle
personally or for commercial purpose because it is easily affordable and the cost of maintenance is very cheap. This
is so because of the poor state of economy in the region.
The principle of thermodynamics has proved that a functioning engine could at times develop one fault or the other
and there is therefore a need to diagnose such fault in order to repair or rectify it. This research work presented an
expert system for diagnosing faults and profound possible solution using artificial intelligence principles.
Different rules are defined using forward chaining and implemented with CLIP programming Language.
1
Nov. 2014. Vol. 5. No. 06 ISSN2305-8269
International Journal of Engineering and Applied Sciences
© 2012 - 2014 EAAS & ARF. All rights reserved
www.eaas-journal.org
Motorcycle just like any other vehicle can develop knowledge base, knowledge engineer, external
fault anywhere and anytime. Under such sources of data and system user.
circumstances, it might be extremely difficult to seek
for the service of mechanical or automobile The second part is Graphical user interface which
engineers. The service of roadside mechanic may not consist of problem solution, Application
also be readily available. programming, problem diagnosis. The third phase is
the system module which consists of reasoning
This research work is out to render a wonderful specification, inference engine knowledge base and
assistance in such situation. The proposed expert user advisor.
system for diagnosing motorcycle faults will also be
of good assistance not only to the owner or the riders Kadarsah [4] developed a decision model for car
but also to engineers and roadside mechanics who faults diagnosis where ES was used to assist car
might have reason to seek for more knowledge or owners, drivers and in experienced mechanics.
assistance why they are on the field.
Milanović et al [2] also developed a motocultivator
When motorcycle developed fault, the rider will have fault diagnosis model using hybridization of ES and
to call for the service of an Automobile engineers or DSS. Nana and Simonov [5] developed a mobile
a roadside mechanic simply because he/she has no vehicle expert system for automobile industry. The
technical skill and knowledge required to diagnose system is made so simple so that vehicle owners and
such faults. Even when the faults is not a major type, drivers can detect their vehicle faults and problems.
the attention of an engineer or expert is still required
otherwise in an attempt to diagnose such fault, a Adsavakulchai [7] developed electric learning (e-
faulty diagnosis may be carried out which further learning) expert system for car fault diagnosis using
aggravate the problem an ground. Dependence on the 19 rules of knowledge base collected from different
expert can be minimized if its expertise can be sources - books, journal, engineering website e.t.c.
documented into computer system [6][9]. Three knowledge base were used – car start
problem, break problem and cooling system problem.
This research work therefore proposes an expert Visual Basic and Microsoft Access were used in the
system for diagnosis of motorcycle faults. Expert implementation of the system.
system is a branch of Artificial Intelligence which
gives the user the opportunity to interact with Nabende [6] in his M.sc thesis developed an expert
computer to solve certain problem. system for diagnosing heavy duty diesel engine
faults. The expert system uses Bayesian network
2. LITERATURE REVIEW technology to represent faults and their related
causes and recommended repair actions.
Different types of expert system have been
developed for various real life applications. A web- 2.1 ARTIFICIAL INTELLIGENT (AI)
based expert system for fish disease diagnosis has METHODS
been developed by Daoliang, Zetian and Yanqing
[3]. The system is being used in North China by fish AI could be defined as a scientific method of making
farmers. Similarly, Ahmad [1] developed an expert machines such as computer capable of exhibiting
system for car failure detection. The systems possess intelligent behaviour.
150 rules to detect different types of failures and
their causes. It divides the system into 3-major parts. The term intelligence covers many cognitive skills
These are start up state, run stable state, movement such as the ability to learn, understand, recognize,
state. and categorize in an attempt to solve real life
problems. Trend of development in the area of AI
Salama et al [10] implemented an Expert Diagnostic today reveals that a lot of progress has been made in
Assistance System for car failure and malfunction. the area of problem solving-concept and method for
This system will be highly useful in assisting developing a system that is capable of reasoning
mechanics for diagnosing vehicle faults. The system about problem, to arrive at a meaningful solution
consists of three (3) major parts. These include – rather than calculating the solution.
knowledge acquisition which capture knowledge
from the domain expert and retain such knowledge in
2
Nov. 2014. Vol. 5. No. 06 ISSN2305-8269
International Journal of Engineering and Applied Sciences
© 2012 - 2014 EAAS & ARF. All rights reserved
www.eaas-journal.org
It comprises of different branches such as Expert partial proposition- partly true or partly false. In such
system, genetic algorithm, fuzzy logic, neural cases, imposing precision may be difficult and may
network e.tc. lead to less optimal solution. Situation of this nature
is better handled by fuzzy system which is able to
2.1.1 Artificial Neural Network (ANN) make effective use of imprecise information by
assigning degree of truth using fuzzy logic. It gives
Human brain consists of 100 billion closely the opportunity of expressing knowledge in vague
interconnected single processing elements known as linguistic terms.
neurons. A simplified model of the neuron and their
operation gave birth to ANN. Series of data which 2.1.4 Expert System (ES)
serve as inputs are used to train the network and
hence produce the appropriate solutions. With Expert system therefore is one of the major areas of
newish data, the system is able to use its past AI that has to do with scientific method of making
experience to solve the problem. If Training or machines to acquire human expert knowledge to
learning phase involved human intervention, it can solve a particular problem in a given domain. Expert
be described as supervised learning or else it is an system can explain why data is needed and how
unsupervised learning. conclusions were reached.
They are very good at solving problem that are not ES can be defined as computer program that combine
prone to algorithmic solutions e.g. pattern expert knowledge in a particular domain and
recognition, decision support etc. It has the ability to disseminate to others. An expert system is a program
handle previously unseen, incomplete or corrupted that emulates the interaction a user might have with a
data. human expert to solve problem in a particular
domain [8].
2.1.2 Genetic Algorithm
The system continues to ask questions from the end
This belongs to a field known as evolutionary user and expect the end user to supply answers as
computation. Process of arriving at meaningful input by selecting one or more from options provided
solution includes: by the system or by entering another set of data as
input. Such interaction will continue until the system
(i) Survival of the fittest reaches the conclusion. The solution arrived at may
(ii) Cross breeding be an exact solution i.e. single solution or multiple
(iii) Mutation solutions arranged in logical order. The system will
equally explain the reason why it arrives at such
In the process, conclusion.
A population of candidate solution is initialized ES has ability to utilize incomplete or incorrect data.
(the chromosomes) In fact, giving only a partial data set, an expert is
New generations of solution are then produced likely to produce accurate result with high degree of
making use of initial population. To produce certainty in its conclusion. The degree of certainty
these solutions, selection, crossover and can be qualified in relative terms and concluded in
mutation are used. knowledge base. The certainty values are assigned by
Next generation are then produced from fitness the expert during the knowledge acquisition place of
function which is used to evaluate the fitness of developing a system.
the newly evaluated solution.
The steps of generating solutions as well as the 2.1.4.1 Advantage of Expert System
evaluation continue until acceptable solution is
found. With expert system in place, the probability and
the frequency of making good decision is high.
2.1.3 Fuzzy System This facilitates a sort of consistency in decision
making. The development of expert system to
Traditional logic is based on proposition. Any solve different real life problem has made it
proposition is either true or false. To solve real life possible to distribute human expert.
problem, there is always a need to make use of
3
Nov. 2014. Vol. 5. No. 06 ISSN2305-8269
International Journal of Engineering and Applied Sciences
© 2012 - 2014 EAAS & ARF. All rights reserved
www.eaas-journal.org
In most cases, the development of expert system Forward Chaining Method: In the development of
will reduce the cost of decision making i.e. the an ES, various rules are put in place. There is
availability of ES make proper and effective use therefore a need to check the condition part of the
of available data. rule to determine truth or false value of such rule. If
It permits objectivity by weighing evidence the condition is true, the action part of the rule is also
without bias and without regards to the user’s true.
personal and emotional reactions.
It made it possible for human expert to have free This process will continue until a solution is arrived
time and mind to concentrate on some other at or a dead end is reached. This approach or method
meaningful activities. is being referred to as data driven reasoning.
ES support modular structure. This thereafter
paves way for high degree of dynalism in solving Backward Chaining: Unlike the forward chaining,
real life problems. the backward chaining is used to backtrack from a
goal to the paths that lead to a goal. Hence, it could
2.1.4.2 Expert System Methods be referred to as goal driven. It has been found
highly applicable when all outcomes are known and
ES adopts different types of methods. Some of these not too large in term of size.
methods include:
2.1.4.3 Components of Expert System
Heuristic Reasoning: This is the type of method the
human expert will adopt in solving problems. It ES is made up of different components that interact
could be referred to as rules thumb or expert together for proper and efficient functionality of the
heuristics. This method allows the expert to arrive at system. Some of the major components of ES
a good conclusion quickly and efficiently. Unlike include knowledge base, inference engine, working
human expert, ES adopt symbolic manipulation with memory, knowledge engineer etc. the integration of
heuristic inference procedure that is very close to these components are illustrated in fig 1 below:
human thinking process. For the ES to adopt this
method, it makes use of the following approach:
(1) Knowledge Base: different types of rules are THEN. These set of rules form the knowledge
set during the development of an ES. The rules base of an ES
are declarative representation of the expertise. (2) Working Storage: one of the major aims of
It is often expressed in the form of IF…….. developing an ES is to solve a particular
problem in a particular domain. The ES would
4
Nov. 2014. Vol. 5. No. 06 ISSN2305-8269
International Journal of Engineering and Applied Sciences
© 2012 - 2014 EAAS & ARF. All rights reserved
www.eaas-journal.org
have to be provided with specific or relevant 1. To analyzed and design an expert system for
data to a problem being solved. Such data diagnosing faults.
constitute the working memory of the ES. 2. To implement the system using clips
(3) Inference Engine: set of code in the ES which programming language
is developed with central aim of drawing 3. To improve the knowledge of motorcycle
inferences or recommendation from knowledge owners and riders in terms of diagnosing
base and problem specific data in the working various faults in motorcycle. This will actually
memory is referred to as inference engine. minimize the maintenance cost of the
(4) User Interface: ES user interacts with the motorcycle.
system. This would not have been possible if 4. To develop an expert system that can be used
there is no link between the system and the as a tool to train inexperienced
user. The code that contains the dialogue mechanical/automobile/motorcycle engineers
between the user and the ES constitute the user in the area of faults diagnosis and repairs in
interface. motorcycle.
(5) Domain Expert: the ES is meant to solve
problem in a particular domain. The main 5. SCOPE AND LIMITATION OF THE
experts are individuals who are expert in RESEARCH
solving the problem. They could be described
as human expert in the specific domain. The Some faults in motorcycle are major and cannot
experience/ knowledge of a domain expert will therefore be solved by the rider or the owner and
be highly regarded in the development of an hence a mechanical/automobile engineer is
ES. consulted. This expert system will serve as a tool to
(6) Knowledge Engineer: the individual that guide the engineers during the diagnosis and repair
encode the expert knowledge in the declarative process. Situations where the fault developed is a
form (making use of set of rules) that can be minor type, the system will guide the rider or the
used by an ES in solving problem in the owner to carry out such basic repair. So, the
domain can be described as Knowledge developed expert system is mostly concerned with
Engineer. minor faults diagnosis and repair. The system will
(7) User: one of the major functions of an expert also be found useful to diagnose some common
system is to provide and make possible solution major faults and add to the knowledge of mechanical
available to the user who will be interacting /automobile engineer in the field. The faults
with the system to get advice/ solution. considered by this system are limited into 3 major
parts. These are:
3. STATEMENT OF THE PROBLEM
1. Faults related to starting of the engine
When a vehicle develops faults, 2. Faults developed while the motorcycle is on
mechanical/automobile engineers are usually motion
employed for repair [5]. The gravity of the vehicle 3. Electrical faults
fault may at times be minor and not so serious to
seek help from an automobile/mechanical engineer. 6. METHODOLOGY
Just like other vehicles, a 2-wheeled vehicle called To develop this system, the following steps were
motorcycle can also developed faults at any time and carried out
hence the attention of a mechanic/engineer is needed
for repair. But the service of such engineer or 1. Identification of the possible faults in
mechanic may not be readily available. Therefore motorcycle.
bicycle owners or riders need a system that will 2. Relevant information was obtained from series
provide immediate solution especially when the of literatures, experienced mechanics and
degree of the fault is quite minimal. engineers were also consulted on how to
diagnose and repair such faults.
4. OBJECTIVES OF THE STUDY 3. The system was designed to categorize the
faults into 3 major classes which include:
The objectives of this research work are: startup, on motion and electrical faults as
shown in fig 2.
5
Nov. 2014. Vol. 5. No. 06 ISSN2305-8269
International Journal of Engineering and Applied Sciences
© 2012 - 2014 EAAS & ARF. All rights reserved
www.eaas-journal.org
;;;===================================
Fig 2: main menu of the system ;;; Expert System For Motorcycle Troubleshooting
;;; This expert system diagnoses some sample problems with a
motorcycle
;;;===================================
;;;********************************
;;;* STARTUP RULES *
;;;********************************
(Defrule Rule1 "Engine Does not Turn-over"
(Selection A1)
(engine turnover no)
(starter turnover no)
(battery ok)
(positive jumper cable starter cable connected)
(big spark turns starter)
(engine turnover no)
=>(printout t "Problem: starter solenoid is Bad")
(printout t "Solution: Replace starter solenoid))
;;;************************************
6
Nov. 2014. Vol. 5. No. 06 ISSN2305-8269
International Journal of Engineering and Applied Sciences
© 2012 - 2014 EAAS & ARF. All rights reserved
www.eaas-journal.org
(A) START UP 13. IF the battery has been replaced AND the engine
is still cranking slowly THEN seek for assistance of
1. IF the motorcycle rider kick the engine over or lit assistance of an experienced mechanical or
the starter button AND the engine does not turn over automobile engineer with reports from rule 11 to 12.
THEN check the starter solenoid.
(B) MOTION
2. IF the starter solenoid clicks and the motorcycle
rider kicks the engine over or hits the starter button 14. IF the motorcycle is shaking or jerking while on
AND the engine still does not turn over THEN the motion THEN the spark plugs are bad and should be
check the charge of the battery.. replaced.
3. IF the battery is fully charged AND the engine 15. IF the spark plugs have been replaced AND the
still do not turn over THEN check the jumper cable, motorcycle is still shaking or jerking while on
connect the positive jumper cable to the starter cable. motion THEN check if there is free flow of fuel
from the carburetor to the engine.
4. IF there is a big spark with the connection in 3,
and starter turns AND the engine still does not turn 16. IF there is no leakage of fuel from carburetor to
over THEN the solenoid is bad and should be the engine AND the motorcycle is still jerking or
replaced. snaking on motion THEN check for air leakage
between the carburetor and the in-let manifold.
5. IF the solenoid has been replaced AND the engine
still does not turn over THEN the starter cable is 17. IF there is no air leakage air leakage between the
broken and should be replaced. carburetor and the in-let manifold AND the
motorcycle is still jerking or snaking on motion
6. IF the starter cable has been replaced AND the THEN seek for assistance of assistance of an
engine still does not turn over THEN the starter is experienced mechanical or automobile engineer with
bad and should be replaced. reports from rule 14 to 16.
7. IF the starter has been replaced AND the engine 18. IF the rider apply the clutch AND the clutch will
still does not turn over THEN connect the positive not disengage THEN the clutch plates has struck
jumper cable to the starter motor together and should be loosed.
8. IF there is a big spark with the connection in 7, 19. IF the clutch plates are struck and making it
and the starter turns THEN the starter gear is bad, impossible for the clutch to disengage THEN the
replace the starter gear loose the plate by running in first or second gear,
pulling-in the clutch and locking up the rear brake.
9. IF the starter gear has been replaced AND the
engine still do not turn over THEN the starter clutch 20. IF rule 18 and 19 cannot free the clutch plate
is bad and should be replaced THEN consult Mechanical or automobile engineer to
take the clutch apart and oil the plate.
10. IF the starter clutch has been replaced AND the
engine still does not turn over THEN the engine is (C) ELECTRICAL
struck. Seek for the assistance of an experienced
mechanical or automobile engineer with reports from 21. IF the rider turns off the engine AND the
rule 1 to 10 headlight is still on THEN there is an electrical
problem, battery terminal should be removed.
11. IF the motorcycle rider turns the key or hit the
start button to start the engine AND the engine is 22. IF the motorcycle rider fixes the battery terminal
cranking slowly making it impossible for the engine back, switches off the headlight AND the light is still
to start THEN check the battery probably it is weak on THEN the fault is not a minor type, an expert
should be consulted with report 21 and 22
7
Nov. 2014. Vol. 5. No. 06 ISSN2305-8269
International Journal of Engineering and Applied Sciences
© 2012 - 2014 EAAS & ARF. All rights reserved
www.eaas-journal.org